C&EN

Energy-Based Coarse-Graining in Molecular Dynamics: A Flow-Based Framework without Data

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. Coarse-grained (CG) models provide an effective route to reduce the complexity of ...
IEEE

Graph Neural Network Enabled Pinching Antennas

Abstract: The pinching-antenna system is a novel flexible-antenna technology, capable of both mitigating large-scale path loss and reconfiguring antenna arrays adaptively. Its core principle relies on ...
IEEE

Graph Neural Network-Based Surrogate Model for Evolutionary Neural Architecture Search

Abstract: Evolutionary neural architecture search (ENAS) is an approach to automating network architecture design. A primary challenge of ENAS is the demand for expensive computational resources, and ...
C&EN

SlaKoNet: A Unified Slater-Koster Tight-Binding Framework Using Neural Network Infrastructure for the Periodic Table

Department of Materials Science and Engineering, Whiting School of Engineering, The Johns Hopkins University, Baltimore, Maryland 21218, United States Department of Electrical and Computer Engineering ...
PNAS

A protein dynamics–based deep learning model enhances predictions of fitness and epistasis

Predicting the effects of multiple mutations on protein function is challenging due to the intricate interplay between residues. Machine learning has advanced these efforts, but traditional neural ...